09:50 – 10:50Tutorial
Abstract to be announced.
Despite the explosive growth of AI, the research community in machine learning (ML) and AI theory remains small and geographically and institutionally dispersed. In Korea, ML/AI theory researchers, especially graduate students, often find themselves isolated within their own labs, with limited opportunities to interact with researchers from other groups.
LeT Workshop aims to promote exchange and collaboration among ML/AI theory researchers across Korea, while providing a venue for sharing their latest research. Internationally, active exchange among researchers has helped build strong research communities that have served as important hubs for advancing AI theory (e.g., ITA Workshop, COLT, ALT, AISTATS, & Simons Institute programs). This workshop aims to provide a similar forum in Korea where such a community can grow.
In line with this goal, this workshop is supported by the National Research Foundation of Korea (NRF) through the R&D project “Development of an End-to-End Design and Validation Framework for Mathematically Principled Next-Generation AI Architectures and Learning Algorithms.” Through this effort, we hope to strengthen the foundation for a self-sustaining ML/AI theory research community in Korea and advance foundational technologies for next-generation AI.
LeT broadly covers theoretical research in machine learning and deep learning, situated at the crossroads of computer science, statistics, mathematics, and related disciplines. We welcome work that primarily advances theoretical analysis and guarantees. Key topics include, but are not limited to:
Design and analysis of learning algorithms, statistical and computational complexity of learning, learning under system constraints, interplay between learning theory and other mathematical fields
Optimization methods for learning, including online and stochastic methods, theory of artificial neural networks including deep learning, theoretical insights into empirical phenomena in learning
Reinforcement learning, bandits, online learning
High-dimensional and non-parametric statistics, Bayesian methods in learning, sampling and probabilistic inference, causality
This workshop was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (Development of an End-to-End Design and Validation Framework for Mathematically Principled Next-Generation AI Architectures and Learning Algorithms, RS-2026-25612350).이 워크샵은 정부(과학기술정보통신부)의 재원으로 한국연구재단의 지원을 받아 수행됨 (수학적 원리 기반 차세대 AI 구조·학습 알고리즘의 전주기 설계·검증 프레임워크 개발, RS-2026-25612350)
A2 · 420 × 594 mmA2 · 420 × 594 mm
